End-to-end Learning for Early Classification of Time Series
Lists
Only you see this
Abstract
Classification of time series is a topical issue in machine learning. While accuracy stands for the most important evaluation criterion, some applications require decisions to be made as early as possible. Optimization should then target a compromise between earliness, i.e., a capacity of providing a decision early in the sequence, and accuracy. In this work, we propose a generic, end-to-end trainable framework for early classification of time series. This framework embeds a learnable decision mechanism that can be plugged into a wide range of already existing models. We present results obtained with deep neural networks on a diverse set of time series classification problems. Our approach compares well to state-of-the-art competitors while being easily adaptable by any existing neural network topology that evaluates a hidden state at each time step.
BibTeX
@inproceedings{ruwurm2023end,
author = {Marc Rußwurm and Sébastien Lefèvre and Nicolas Courty and Rémi Emonet and Marco Körner and Romain Tavenard},
title = {{End-to-end Learning for Early Classification of Time Series}},
booktitle = {ISPRS},
year = {2023},
doi = {10.1016/j.isprsjprs.2022.12.016},
}